dmonscilearncluster.py 文件源码

def sdbscanTrain(self, settings, mname, data):
        '''
        :param data: -> dataframe with data
        :param settings: -> settings dictionary
        :param mname: -> name of serialized clusterer
        :return: -> clusterer
        :example settings: -> {eps:0.9, min_samples:10, metric:'euclidean' ,
        algorithm:'auto, leaf_size:30, p:0.2, n_jobs:1}
        '''
        for k, v in settings.iteritems():
            logger.info('[%s] : [INFO] SDBSCAN %s set to %s',
                         datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), k, v)
            print "SDBSCAN %s set to %s" % (k, v)
        sdata = StandardScaler().fit_transform(data)
        try:
            db = DBSCAN(eps=float(settings['eps']), min_samples=int(settings['min_samples']), metric=settings['metric'],
                        algorithm=settings['algorithm'], leaf_size=int(settings['leaf_size']), p=float(settings['p']),
                        n_jobs=int(settings['n_jobs'])).fit(sdata)
        except Exception as inst:
            logger.error('[%s] : [ERROR] Cannot instanciate sDBSCAN with %s and %s',
                           datetime.fromtimestamp(time.time()).strftime('%Y-%m-%d %H:%M:%S'), type(inst), inst.args)
            print "Error while  instanciating sDBSCAN with %s and %s" % (type(inst), inst.args)
            sys.exit(1)
        labels = db.labels_
        print labels
        n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)
        print'Estimated number of clusters: %d' % n_clusters_
        self.__serializemodel(db, 'sdbscan', mname)
        return db